© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50599
    Prev
    Next
    INDEX
    Explanations

    classroom and its surroundings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boll
    -0.09
    awning
    -0.08
    IKE
    -0.08
    ãĥ¼ãĤº
    -0.08
    ikken
    -0.08
    asters
    -0.08
    -MM
    -0.08
    \OptionsResolver
    -0.08
    ampe
    -0.08
    åħ¬åı¸åĨħéĥ¨
    -0.07
    POSITIVE LOGITS
    æķĻ室
    0.09
    room
    0.08
    çıŃ
    0.08
    éĵĥ
    0.08
    纪å¾ĭ
    0.08
     mevc
    0.07
    课éĹ´
    0.07
    常è§Ħ
    0.07
    roll
    0.07
    åIJİæİĴ
    0.07
    Activations Density 0.065%

    No Known Activations